Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to exclusion and inclusion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inclusion and exclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pressing
    -0.77
     recomb
    -0.72
     metab
    -0.68
     braking
    -0.68
     biom
    -0.67
    Ü
    -0.66
     cumbers
    -0.64
     abort
    -0.64
     flowing
    -0.63
     accelerating
    -0.62
    POSITIVE LOGITS
    olean
    0.84
    pread
    0.84
    jury
    0.83
    odore
    0.83
    utenant
    0.83
    juries
    0.81
    naire
    0.80
    berra
    0.77
    agues
    0.77
    advertising
    0.77
    Act Density 0.043%

    No Known Activations